reasoning is overpriced
labs bill you for noise.
noise → signal
verbosedense0%
tokens: 48cost: $0.48answer: 42 ✓
overpriced since everyone missed token density. no one is scaling it. no AGI without it.
vision →work
AdaPrefix-GRPOnew
max out RL signal on problems model never solves
Agonnew
two models compete by reading each other's reasoning
Vladislav Beliaev
RL researcher, founding engineer, 8+ years →